About this Research Topic
Semantic SLAM, or semantic mapping, combines SLAM with object identification. SLAM contains only geometric data of the environment, while in semantic analysis objects are recognized in the surroundings. Combining these techniques makes it possible to create maps with semantic information that provide mobile robots with better and enhanced navigation, as well as task planning capabilities. For example, in hospitals, a robot could safely navigate and interact in places with a high risk of contagion, preventing a person from being exposed to diseases, such as the hospital attendants who were directly exposed to COVID-19.
As robots and humans are increasingly sharing the same environment, robots are more and more required to move safely in these dynamic, unknown and indoor/outdoor environments. Just as human beings behave in an environment, avoiding obstacles and respecting the personal space of other individuals, robots should show the same behaviors. This requires the development of autonomous navigation systems, based on SLAM, that consider semantic information as object information, integrate localization, mapping and navigation tasks.
In localization, the main objective is to estimate the position and orientation of the robot. A representation of the environment is realized as a map and in navigation tasks a best path is selected. Identifying objects using a vision and recognition system (which consists of classifying and locating objects in an environment) can further enhance navigation, as in this way additional information is introduced, creating more complex maps of the environment (semantic maps) that provide information on where and which objects are close to the robot. This can better guide the robot through the environment.
The Research Topic is interesting for publications related to Robotics and AI applications. Therefore, the scope of this Research Topic includes, but is not limited to, the following topics:
• Applications for Mobile Robot Navigation;
• Application of Machine Learning in SLAM Algorithms.
• Visual SLAM;
• Multi-Robot SLAM;
• Semantic SLAM
Keywords: Semantic SLAM, SLAM, Localization, Mapping, Navigation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.